Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
J_SEE_MODELYesVision model name (must be set explicitly)
J_SEE_TOKENYesVision model API key (not hardcoded — must be set explicitly)
J_SEE_API_SPECNoUpstream API spec: responses / openai / anthropicresponses
J_SEE_BASE_URLYesVision endpoint base URL (must match J_SEE_API_SPEC; trailing slashes are stripped)
J_SEE_MAX_EDGENoMax long-edge pixels for image compression1568
J_SEE_MAX_BYTESNoMax source file size in bytes; larger is rejected52428800
J_SEE_REASONINGNoReasoning effort (only honored by the openai spec): none / low / medium / highnone
J_SEE_TIMEOUT_MSNoVision call timeout in milliseconds90000

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
see_imageA

读取图片(本地文件 / URL / 剪贴板 / 最近截图)并通过视觉模型返回文字描述。用于主模型无多模态输入能力时的识图。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/PichurChill/j-can-see'

If you have feedback or need assistance with the MCP directory API, please join our Discord server